MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization

• URL: http://arxiv.org/abs/2602.03537v1
• Date: Tue, 03 Feb 2026 13:52:18 GMT
• Title: MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
• Authors: Maximilian Kleinegger, Elvir Crnčević, Dan Alistarh,
• Abstract summary: Matryoshka Quantization (MatQuant) is a recent quantization approach showing that a single integer-quantized model can be served across multiple precisions.<n>We introduce Post-Training Matryoshka Quantization (MatGPTQ), a new PTQ pipeline that produces a single parent model jointly optimized for multiple target precisions in one-shot.
• Score: 35.18619976978831
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Matryoshka Quantization (MatQuant) is a recent quantization approach showing that a single integer-quantized model can be served across multiple precisions, by slicing the most significant bits (MSB) at inference time. This enables a single checkpoint to cover a wide range of memory and latency budgets, but renders quantization much more challenging. In particular, the initial MatQuant relies on expensive quantization-aware training (QAT) variants, rather than fast one-shot post training quantization (PTQ), and lacks open-source and kernel support. We address all of these limitations by introducing Post-Training Matryoshka Quantization (MatGPTQ), a new PTQ pipeline that produces a single parent model jointly optimized for multiple target precisions in one-shot, based on a small calibration set. MatGPTQ casts Matryoshka quantization as a multi-precision objective with bit-slicing and cross-bit error compensation, resulting in an algorithm that produces a multi-bit-width, "sliceable" model in a single pass. We also incorporate a new budget-aware search for heterogeneous per-layer bit-witdhs and provide efficient kernels that implement slicing and mixed-precision execution. Across standard LLMs and benchmarks, MatGPTQ preserves high-bit accuracy while substantially improving performance at low-bit-witdh settings. Overall, we establish a new state of the art for Matryoshka-style post-training quantization and make single-checkpoint, multi-precision deployment open and practical. Code is available at https://github.com/IST-DASLab/MatGPTQ.

Related papers

• Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression [57.54335545892155]
  We introduce a Grouped Lattice Vector Quantization (GLVQ) framework that assigns each group of weights a customized lattice codebook.<n>Our approach achieves a better trade-off between model size and accuracy compared to existing post-training quantization baselines.
  arXiv  Detail & Related papers  (2025-10-23T20:19:48Z)
• QSpec: Speculative Decoding with Complementary Quantization Schemes [53.960146187821685]
  Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs)<n>We propose QSpec, a novel quantization paradigm that decouples efficiency from quality.<n>QSpec reuses both weights and KV cache across stages, enabling near-zero-cost switching without retraining or auxiliary models.
  arXiv  Detail & Related papers  (2024-10-15T05:57:51Z)
• EfficientQAT: Efficient Quantization-Aware Training for Large Language Models [50.525259103219256]
  quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss.<n>We propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm.<n> EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP)
  arXiv  Detail & Related papers  (2024-07-10T17:53:30Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [63.118592279833656]
  Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs)<n>We propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise.<n> Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search [7.564770908909927]
  Quantization is a technique for creating efficient Deep Neural Networks (DNNs) We propose MixQuant, a search algorithm that finds the optimal custom quantization bit-width for each layer weight based on roundoff error. We show that combining MixQuant with BRECQ, a state-of-the-art quantization method, yields better quantized model accuracy than BRECQ alone.
  arXiv  Detail & Related papers  (2023-09-29T15:49:54Z)
• Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming [7.0146264551420066]
  Quantization is a widely used technique to compress neural networks.<n>MPQ addresses this by assigning varied bit-widths to layers, optimizing the accuracy-efficiency trade-off.<n>We introduce CLADO, a practical sensitivity-based MPQ algorithm that captures crosslayer dependency of quantization error.
  arXiv  Detail & Related papers  (2023-07-11T15:56:00Z)
• Towards Efficient Post-training Quantization of Pre-trained Language Models [85.68317334241287]
  We study post-training quantization(PTQ) of PLMs, and propose module-wise quantization error minimization(MREM), an efficient solution to mitigate these issues. Experiments on GLUE and SQuAD benchmarks show that our proposed PTQ solution not only performs close to QAT, but also enjoys significant reductions in training time, memory overhead, and data consumption.
  arXiv  Detail & Related papers  (2021-09-30T12:50:06Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization [32.770842274996774]
  Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks. Previous methods either examine only a small manually-designed search space or utilize a cumbersome neural architecture search to explore the vast search space. This work proposes bit-level sparsity quantization (BSQ) to tackle the mixed-precision quantization from a new angle of inducing bit-level sparsity.
  arXiv  Detail & Related papers  (2021-02-20T22:37:41Z)
• Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision [20.081543082708688]
  We propose multipoint quantization, a method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers. We show that our method outperforms a range of state-of-the-art methods on ImageNet classification and it can be generalized to more challenging tasks like PASCAL VOC object detection.
  arXiv  Detail & Related papers  (2020-02-20T22:37:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.